Sign inGet started
Skills / Business-strategy

Flywheel Model

There is no single defining action, no grand program, no one killer innovation, no solitary lucky break, no miracle moment. Rather, the process resembles relentlessly pushing a giant, heavy flywheel, turn upon turn, building momentum until a point of breakthrough, and beyond.

Jim Collins' Flywheel Model is a strategic framework for building compound organizational momentum through a series of causally linked stages that each accelerate the next. Unlike strategies built around singular dramatic moves, the Flywheel traces how great companies — Amazon, Vanguard, Intel — achieved dominance by identifying their unique virtuous cycle and pushing it with disciplined consistency. This skill guides you through discovering, mapping, auditing, and extending your own flywheel so momentum builds on itself rather than being squandered in reactive pivots.

By Jim Collins · Free
Specimen 01 · Live diagnosisFlywheel Model
Input

“We're a B2B SaaS company. When we land enterprise customers, our product gets more integrations built for it, which makes it easier to sell to the…”

Diagnosis
Collins' research is clear: there's no single defining move that creates breakthrough results — only the flywheel.
Full transcript ↓
Calibrated referenceagent-skills.ai
The gap

Stop chasing breakthroughs — build the self-reinforcing cycle that makes them inevitable

The Flywheel Model holds that organizational breakthroughs emerge from compound momentum — not from any single dramatic initiative. Practitioners map a 4–6 stage virtuous cycle in which each stage causally feeds the next and the final stage loops back to reinforce the first. Amazon's classic flywheel illustrates the structure: lower prices drive more customer visits, which attract more third-party sellers, which expand selection, which improves customer experience, which allows lower cost structures, which permit even lower prices. Collins introduces an equally important counter-pattern — the Doom Loop — in which reactive reorganizations, leapfrog strategies, and abandoned initiatives dissipate accumulated momentum before it can compound. The skill produces a concrete artifact: a labeled flywheel diagram with defined causal connections, a designated top-of-flywheel starting point, and measurable indicators at each stage. Advanced application extends a proven flywheel into new markets without sacrificing core momentum.

The problem

Leaders default to searching for the single bold move — the transformative hire, the new initiative, the pivot — that will unlock breakthrough results. This pattern, which Collins names the Doom Loop, destroys the accumulated momentum that consistent, compounding effort would have produced. The result is a perpetual cycle of promising starts and abandoned strategies, each one resetting the flywheel to zero.

The solution

By the end of this conversation, you will have a named, causally coherent flywheel — not a list of aspirations, but a self-reinforcing cycle specific to your organization — along with the Doom Loop patterns you must stop in order to let it turn.

You bring
  • A description of your organization, product, or team and what it does
  • Your current strategic priorities, initiatives, or growth bets
  • Any sense of what is working and what keeps stalling despite effort
  • Willingness to challenge whether current activities reinforce each other causally
You get
  • A labeled 4–6 stage flywheel diagram with causal connections and a defined starting push point
  • A Doom Loop contrast showing which current patterns are dissipating your momentum
  • Specific, measurable indicators for each flywheel stage so you can track whether the cycle is turning
  • A strategic narrative built around your flywheel that aligns leadership on what to push — and what to stop
In action

Watch the methodology work.

Three specimens from a single real session: the same situation, unaided and calibrated, the full transcript, and the skill answering live in the channel where the work happens.

Fig.01The same situation, two ways
Specimens A · B
Specimen AVague
Unaided

“You have a strategy deck with seven pillars, three new initiatives launching this quarter, and a leadership team debating whether to push deeper into enterprise or expand into mid-market. Last year's top priority — the partner ecosystem — got deprioritized when a big enterprise deal required custom work. The year before, you pivoted from a channel strategy after six months. Results are good but not compounding.”

×Vague — nothing concrete to act on.
Specimen BCalibrated
With Flywheel Model

“You have a four-stage flywheel with named causal connections, a designated starting push point (enterprise reference development), and a KPI for each stage. Your leadership team has agreed on one Doom Loop behavior to stop this quarter — accepting custom development that doesn't generalize to the platform. New initiatives are evaluated against a single question: does this push the flywheel, or does it reset it?”

Specific, grounded, and ends with one clear next step.
Fig.02A real session, unedited
In-app · assistant
Flywheel ModelClaude
Flywheel Model
Collins' research is clear: there's no single defining move that creates breakthrough results — only the flywheel. Before we build yours, I need to understand what actually drives outcomes in your organization right now. Not what you want to be true, but what's demonstrably working. What's the one thing, when it happens more, that seems to cause other good things to follow?
We're a B2B SaaS company. When we land enterprise customers, our product gets more integrations built for it, which makes it easier to sell to the next enterprise customer.
That's the seed of a flywheel — enterprise customers pull integrations, integrations pull more enterprise customers. But we need to close the causal loop and fill in the middle. What happens between 'enterprise customer goes live' and 'integrations get built'? Who builds those integrations — your team, partners, the customers themselves? And what's the mechanism: is it that enterprise logos signal legitimacy to integration partners, or that enterprise contracts fund your integration roadmap, or something else?
Both, actually. Enterprise contracts give us budget to build integrations ourselves, and enterprise logos convince mid-market SaaS tools to build native integrations because they want access to our customer base.
Good — you actually have two reinforcing mechanisms at that stage, which is a strength. Let me map what we have so far and flag where the causal logic needs one more stage to be complete:
1.
Enterprise Customer Acquisition → Provides budget AND signals legitimacy2. Integration Ecosystem Expansion (your team builds + partners self-select in)3. Reduced Switching Cost / Stickiness → Enterprise customers embed deeper4. [Gap] → What does deeper embedding or more integrations do that feeds back to Stage 1?
I suspect the missing stage is something like 'integration ecosystem becomes a moat that competitors can't replicate' — which means your sales team can go back to similar enterprise prospects with a defensible story. Does that land, or does the cycle return to Stage 1 through a different path?
Yes — it also creates case studies and reference customers. Our enterprise sales cycle is largely reference-driven. So existing enterprise customers give us references, which close new enterprise customers.
Now the loop closes cleanly. Here's your flywheel draft:
1.
Enterprise Reference Customers → Credibility with new prospects2. New Enterprise Wins → Budget + logo legitimacy3. Integration Ecosystem Growth → Platform depth and partner network4. Deep Customer Embeddedness → Expanded reference pool and case study library→ loops back to Stage 1
The top of the flywheel — your first disciplined push — is Stage 1: investing disproportionately in making your first wave of enterprise customers into active, referenceable advocates. Not passive logos, but customers who will take calls. Now let's check for the Doom Loop: are there places where your organization is currently doing something that breaks this cycle — for example, chasing mid-market volume that dilutes your enterprise brand, or building features for individual customers that don't expand the integration ecosystem?
Honestly, yes — we keep getting pulled into custom work for individual enterprise customers that doesn't generalize. It keeps our retention up but it's not building the platform.
That's a textbook Doom Loop entry point. Custom work feels like it's reinforcing the flywheel — you're keeping enterprise customers — but it's actually a slow leak. Each custom engagement consumes engineering capacity that would otherwise expand the integration ecosystem, and custom features don't produce reference-able use cases because they don't exist in the product other prospects will buy. Collins calls this 'the undisciplined pursuit of more' — doing adjacent things that look productive but don't push the flywheel. The fix isn't to stop serving enterprise customers; it's to define a clear policy: custom requests get evaluated against whether they can become a generally available integration within 90 days. If yes, build it. If no, decline or charge a premium that offsets the flywheel cost.
Reply to Flywheel Model
What the skill is doing
01Flywheel Discovery Interview
02Doom Loop Diagnosis
03Stage Mechanics Mapping
Fig.03The same skill, in the channel you already use
WhatsApp · live
9:41
FMFlywheel Modeltyping…
Messages are end-to-end encrypted. No one outside of this chat can read them.
Today
We're a B2B SaaS company. When we land enterprise customers, our product gets more integrations built for it, which makes it easier to sell to the nex…9:14✓✓
Collins' research is clear: there's no single defining move that creates breakthrough results — only the flywheel.9:14
Before we build yours, I need to understand what actually drives outcomes in your organization right now.9:15
Not what you want to be true, but what's demonstrably working.9:15
Message

The same skill, where the work happens.

No new app to learn. The methodology runs over the WhatsApp Business API, so the answer lands as a reply in the thread you’re already in — same rigour, zero context-switch.

Reads the situation, names the pattern, returns one concrete next move.
Delivered in seconds, inside a conversation that already exists.
Specimen · WhatsApp Business API · live
Capabilities

What it does, specifically.

Each capability is a distinct move drawn straight from the source methodology — not a generic assistant guessing.

CapabilityC-01

Flywheel Discovery Interview

Through a structured series of questions about what drives results in your organization, this capability surfaces the 4–6 causal stages that form your unique virtuous cycle. The emphasis is on causal linkage — each stage must mechanically feed the next — rather than a wishful list of goals.

Based on Collins' core flywheel construction process from Turning the Flywheel, which requires each stage to have a demonstrable cause-and-effect relationship with the next, ultimately looping back to reinforce the starting point.
CapabilityC-02

Doom Loop Diagnosis

Audits your current strategic behavior against the Doom Loop pattern: reactive reorganizations, leapfrog pivots to unproven new directions, programs that replace prior programs before they compound, and leadership changes that reset strategic direction. Each identified Doom Loop pattern is contrasted with its flywheel alternative.

Directly derived from Collins' Doom Loop concept in Good to Great, which documents how comparison companies — those that failed to sustain greatness — consistently disrupted their own momentum through reactive strategy changes rather than disciplined consistency.
CapabilityC-03

Stage Mechanics Mapping

Moves each flywheel stage from abstract concept to concrete mechanism by defining the specific actions, decisions, and investments that push that stage forward, along with observable leading indicators that signal the stage is gaining momentum.

Implements Collins' instruction from Turning the Flywheel to define the 'specific mechanisms' at each stage — the difference between 'great customer experience' (abstract) and 'same-day delivery fulfillment rate' (measurable stage indicator).
CapabilityC-04

Flywheel Benchmarking

Compares your flywheel structure against Collins' documented examples — Amazon (selection and price), Vanguard (low-cost indexing and investor returns), and Intel (Moore's Law manufacturing and developer ecosystem) — to identify structural gaps or opportunities in your own cycle's design.

Collins explicitly provides worked flywheel examples in Turning the Flywheel to enable cross-company structural comparison, noting that while the specific stages differ by organization, the causal loop architecture follows consistent patterns across great companies.
CapabilityC-05

Momentum Extension Planning

Guides you through applying an established flywheel to a new market, product category, or organizational arena — maintaining the core causal structure while adapting stage mechanics to new context. This prevents growth moves that accidentally break the flywheel rather than extend it.

Addresses Collins' advanced concept of 'turning the flywheel into a platform,' in which a proven virtuous cycle becomes the engine for adjacent expansion without requiring the organization to restart momentum from zero.
Tested

Graded before it shipped.

Every skill is scored against independent scenarios for methodology fidelity before it goes live — not vibes, a rubric.

What it produces
OutputD-01

Flywheel Stage Map

A labeled diagram of your 4–6 stage virtuous cycle, with each stage named, its causal connection to the next stage specified, a designated top-of-flywheel starting point, and a measurable indicator per stage. This is the primary strategic artifact Collins describes in Turning the Flywheel.

OutputD-02

Doom Loop Contrast Analysis

A side-by-side comparison of your flywheel's required behaviors versus the Doom Loop patterns currently present in your organization — showing exactly where reactive decision-making is resetting the flywheel and what disciplined alternative each behavior requires.

OutputD-03

Stage KPI Dashboard

A set of leading and lagging indicators for each flywheel stage, designed to let you track whether each stage is actually building momentum or stalling — giving you an early warning system before the whole cycle loses speed.

The source

Grounded in the original work.

Every answer traces back to a real source and the practitioner who wrote it — not a secondhand summary. Here is the source of record.

Source authorA-01

Jim Collins

Jim Collins is a management researcher and author whose book Good to Great (2001) has sold over 4 million copies and remains one of the best-selling business books of all time. A former faculty member at Stanford Graduate School of Business, Collins runs a management research laboratory in Boulder, Colorado, where he studies enduring great companies. His body of work — including Built to Last and Great by Choice — is grounded in rigorous longitudinal research comparing companies that achieved sustained greatness with comparable firms that did not.

Status · Inspired by Jim Collins’s work — not yet claimed. Are you Jim Collins?
Primary sourceS-01

Good to Great (2001) and Turning the Flywheel: A Monograph to Accompany Good to Great (2019)

by Jim Collins

Author of Good to Great (4M+ copies sold), former Stanford GSB faculty, management researcher with decades of comparative company studies.

Read the original ↗
Citationjimcollins.com
In the build queue

Be first to run it.

Flywheel Model is being built right now. Leave your email and we’ll tell you the moment it goes live.

Notify meEmail
At launchI want to build a flywheel for my organization but I'm not sure if what I have is a real causal cycle or just a list of things I hope will work together. Can you interview me to find out?